scispace - formally typeset
Search or ask a question
Author

Joshi Manisha Shivaram

Bio: Joshi Manisha Shivaram is an academic researcher from B.M.S. College of Engineering. The author has contributed to research in topics: Diabetic foot & Thermography. The author has an hindex of 4, co-authored 9 publications receiving 47 citations.

Papers
More filters
Book ChapterDOI
01 Jan 2019
TL;DR: This chapter will give the reader a solid understanding of the theory behind infrared thermography and the use of soft computing techniques applied to medical image analysis, particularly for diabetic foot complication assessment.
Abstract: Recent advancements in digital image processing and soft computing techniques have widened the scope of computer aided diagnosis of medical conditions. Many imaging modalities like MRI, CT, PET, Ultrasound combined with soft computing techniques is already contributing to this trend. With the recent inclusion of infrared thermal imaging, the capability of computer aided diagnosis has increased and has become more safe and convenient. Research in this noncontact and noninvasive imaging technology has steadily increased over the last 50 years. Disease diagnosis based on the correlation of surface temperature distribution of skin is being studied at large and has shown promising results. This chapter will give the reader a solid understanding of the theory behind infrared thermography and the use of soft computing techniques applied to medical image analysis, particularly for diabetic foot complication assessment. The issues and challenges to be addressed in using infrared thermography for diagnostic purposes are also discussed. The reader will get a complete overview of building an intelligent diagnostic system using the two sensational topics of research in machine learning and medical imaging—infrared thermography and soft computing.

23 citations

01 Jan 2009
TL;DR: These automatically detected haemorrhages are validated by comparing with expert ophthalmologists' hand-drawn ground-truths and the overall sensitivity, specificity and PV obtained are 89.49, 99.89, and 98.34% respectively.
Abstract: We propose an algorithm for the detection of Haemorrhages from Diabetic Retinopathy images. The algorithm proceeds through three main steps 1. Color image enhancement 2.Image subtraction to extract blood vessels and haemorrhages and 3.Use of set of optimally adjusted morphological operators to suppress blood vessels and to highlight only haemorrhages. These automatically detected haemorrhages are validated by comparing with expert ophthalmologists' hand-drawn ground-truths. Quantitative performance of our algorithm is evaluated by calculating sensitivity and specificity and predictive value (PV). The overall sensitivity, specificity and PV obtained are 89.49%, 99.89%, and 98.34% respectively.

22 citations

Journal Article
TL;DR: This project presents the portable prototype of Nadi Pariksha Yantra for pulse reading and analysis which is normally used by an ayurvedic practitioner and will be useful in prognosis of the cardiac disorders.
Abstract: The population in the world is increasing enormously and so the people suffering from cardiovascular diseases. In future there is a need for introduction of system which can help in early diagnostics of human health. Now-a-days in medical field there are different methods to examine the pulse of a patient but their basic concepts, clinical methods and practices are not identical. These concepts are arrived from our own ayurvedic practices. The main aim of this research is to design a non-invasive system based on ancient diagnostic technique of Nadi Pariksha (Pulse Detection) to assist doctors in routine diagnostic procedures. Nadi Pariksha is one of the ancient medical technologies, originated in India and China. This technique is derived from Ayurveda. Wrist pulse analysis for identification of health status is found in ancient Indian as well as Chinese literature. This project presents the portable prototype of Nadi Pariksha Yantra for pulse reading and analysis which is normally used by an ayurvedic practitioner. This would also be helpful to other physicians who are not well trained to this ancient technique and will be useful in prognosis of the cardiac disorders. Keywords—Nadi pariksha, Radial Artery, Pre-processing, Data acquisition, Classification, LabView.

13 citations

Proceedings ArticleDOI
03 Apr 2018
TL;DR: The infrared thermal images of 62 diabetic and 20 healthy subjects were analyzed to identify the temperature distribution patterns capable of detecting diabetic foot complications and these patterns were taken using Fluke TiX560 thermal imager.
Abstract: Diabetic foot complications are a major cause of concern for diabetic patients as it affects mobility and quality of life. Any computer aided diagnosis system would be very useful in the early detection and hence treatment and cure. For such a system, the surface temperature distribution patterns in the plantar region of the foot of both healthy and diabetic subjects have to be analyzed to detect any abnormality. In this paper we have analyzed the infrared thermal images of 62 diabetic and 20 healthy subjects to identify the temperature distribution patterns capable of detecting diabetic foot complications. The images were taken using Fluke TiX560 thermal imager. Image processing and analysis was done in MATLAB.

7 citations

Proceedings ArticleDOI
01 Feb 2017
TL;DR: A semi-automatic segmentation algorithm is proposed and implemented in MATLAB to segment the foot from thermal images taken using Fluke TiX560 thermal imaging camera and has shown promising results.
Abstract: Digital Infrared Thermal Imaging (DITI) or Infrared Thermography is a non-invasive, non-contact, harmless technique which measures and records the surface temperature of the skin under study as thermogram or thermal images. Segmentation of the region of interest from thermal images is a very difficult task especially with the foot because of the presentation of the ankle bones in the images and the temperature difference between the foot and background being small which interfere with the segmentation task. Our segmentation procedure is an attempt to work on these challenges and has shown promising results. In this paper, a semi-automatic segmentation algorithm is proposed and implemented in MATLAB to segment the foot from thermal images taken using Fluke TiX560 thermal imaging camera. Image Acquisition protocol plays a very important role in successful segmentation of thermal images. Images acquired using different setups at three different occasions are considered for the current study. Segmentation outcome of our method is analyzed using the three measures such as Jaccard index, False Positive Rate and False Negative Rate in comparison with the result of manual segmentation.

6 citations


Cited by
More filters
Journal Article
TL;DR: Sub stantial evidence supports screening all patients with diabetes to identify patients at risk for foot ulceration, including patient education, prescription footwear, intensi ve podiatric care, and evaluation for surgical interventions.
Abstract: Context:Among persons diagnosed as having diabetes mellitus, the prevalence of foot ulcers is 4%to 10%, the annual population-based incidence is 1.0%to 4.1 %, and the lifetime incidence may be as high as 25%. These ulcers frequently b ecome infected, cause great morbidity, engender considerable financial costs, an d are the usual first step to lower extremity amputation. Objective:To systemat ically review the evidence on the efficacy of methods advocated for preventing d iabetic foot ulcers in the primary care setting. Data Sources, Study Selection, and Data Extraction:The EBSCO, MEDLINE, and the National Guideline Clearinghous e databases were searched for articles published between January 1980 and April 2004 using database-specific keywords. Bibliographies of retrieved articles wer e also searched, along with the Cochrane Library and relevant Web sites. We revi ewed the retrieved literature for pertinent information, paying particular atten tion to prospective cohort studies and randomized clinical trials. Data Synthesi s:Prevention of diabetic foot ulcers begins with screening for loss of protecti ve sensation, which is best accomplished in the primary care setting with a brie f history and the Semmes-Weinstein monofilament. Specialist clinics may quantif y neuropathy with biothesiometry, measure plantar foot pressure, and assess lowe r extremity vascular status with Doppler ultrasound and ankle-brachial blood pr essure indices. These measurements, in conjunction with other findings from the history and physical examination, enable clinicians to stratify patients based o n risk and to determine the type of intervention. Educating patients about prope r foot care and periodic foot examinations are effective interventions to preven t ulceration. Other possibly effective clinical interventions include optimizing glycemic control, smoking cessation, intensive podiatric care, debridement of c alluses, and certain types of prophylactic foot surgery. The value of various ty pes of prescription footwear for ulcer prevention is not clear. Conclusions:Sub stantial evidence supports screening all patients with diabetes to identify thos e at risk for foot ulceration. These patients might benefit from certain prophyl actic interventions, including patient education, prescription footwear, intensi ve podiatric care, and evaluation for surgical interventions.

597 citations

Patent
06 Apr 2012
TL;DR: In this article, the authors present methods and devices for diagnosing and predicting the presence, progression and/or treatment effect of a disease characterized by retinal pathological changes in a subject.
Abstract: The present application provides methods and devices for diagnosing and/or predicting the presence, progression and/or treatment effect of a disease characterized by retinal pathological changes in a subject.

88 citations

Journal ArticleDOI
22 Mar 2020-Sensors
TL;DR: This paper compares machine learning-based techniques with Deep Learning (DL) structures and designs a new DL-structure, which is trained from scratch and is able to reach higher values in terms of accuracy and other quality measures, highlighting their advantages and limitations.
Abstract: According to the World Health Organization (WHO), Diabetes Mellitus (DM) is one of the most prevalent diseases in the world. It is also associated with a high mortality index. Diabetic foot is one of its main complications, and it comprises the development of plantar ulcers that could result in an amputation. Several works report that thermography is useful to detect changes in the plantar temperature, which could give rise to a higher risk of ulceration. However, the plantar temperature distribution does not follow a particular pattern in diabetic patients, thereby making it difficult to measure the changes. Thus, there is an interest in improving the success of the analysis and classification methods that help to detect abnormal changes in the plantar temperature. All this leads to the use of computer-aided systems, such as those involved in artificial intelligence (AI), which operate with highly complex data structures. This paper compares machine learning-based techniques with Deep Learning (DL) structures. We tested common structures in the mode of transfer learning, including AlexNet and GoogleNet. Moreover, we designed a new DL-structure, which is trained from scratch and is able to reach higher values in terms of accuracy and other quality measures. The main goal of this work is to analyze the use of AI and DL for the classification of diabetic foot thermograms, highlighting their advantages and limitations. To the best of our knowledge, this is the first proposal of DL networks applied to the classification of diabetic foot thermograms. The experiments are conducted over thermograms of DM and control groups. After that, a multi-level classification is performed based on a previously reported thermal change index. The high accuracy obtained shows the usefulness of AI and DL as auxiliary tools to aid during the medical diagnosis.

65 citations

Proceedings ArticleDOI
16 May 2012
TL;DR: Techniques, algorithms, and methodologies used for the detection of hemorrhage from diabetic retinopathy retinal images are reviewed.
Abstract: Diabetic Retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. The presence of hemorrhages in the retina is the earliest symptom of diabetic retinopathy. The number and shape of hemorrhages is used to indicate the severity of the disease. Early automated hemorrhage detection can help reduce the incidence of blindness. In this paper we review techniques, algorithms, and methodologies used for the detection of hemorrhage from diabetic retinopathy retinal images.

56 citations

Journal ArticleDOI
TL;DR: In this article, the authors compared a machine learning-based scoring technique with feature selection and optimization techniques and learning classifiers to several state-of-the-art Convolutional Neural Networks (CNNs) on foot thermogram images and proposed a robust solution to identify the diabetic foot.

41 citations