In the past decade, the field of medical image analysis has grown exponentially, with an increased number of pattern recognition tools and an increase in data set sizes. These advances have facilitated the development of processes for high-throughput extraction of quantitative features that result in the conversion of images into mineable data and the subsequent analysis of these data for decision support; this practice is termed radiomics. This is in contrast to the traditional practice of treating medical images as pictures intended solely for visual interpretation. Radiomic data contain first-, second-, and higher-order statistics. These data are combined with other patient data and are mined with sophisticated bioinformatics tools to develop models that may potentially improve diagnostic, prognostic, and predictive accuracy. Because radiomics analyses are intended to be conducted with standard of care images, it is conceivable that conversion of digital images to mineable data will eventually become routine practice. This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision making, particularly in the care of patients with cancer.

https://pubs.rsna.org/doi/pdf/10.1148/radiol.2015151169

Radiomics: Images Are More than Pictures, They Are Data.

https://medicinainternaucv.files.wordpress.com/2013/02/exceso-de-confianza-como-causa-de-error-diagnc3b3stico.pdf

Overconfidence as a cause of diagnostic error in medicine.

Background
Magnetic resonance imaging (MRI) is increasingly being used for rectal cancer staging. The purpose of this study was to determine the accuracy of phased array MRI for T category (T1–2 vs. T3–4), lymph node metastases, and circumferential resection margin (CRM) involvement in primary rectal cancer.

/pdf/diagnostic-accuracy-of-mri-for-assessment-of-t-category-4w0o2h0qa7.pdf

Diagnostic Accuracy of MRI for Assessment of T-category, Lymph Node Metastases, and Circumferential Resection Margin Involvement in Patients with Rectal Cancer: A Systematic Review and Meta-analysis

BACKGROUND

Advances in the diagnosis and treatment of breast carcinoma have led to a multidisciplinary approach to management for patients with breast carcinoma. To assess the effect of this approach, the authors performed an evaluation for a cohort of patients examined in a multidisciplinary breast cancer center.



METHODS

An analysis was performed for the records of 75 consecutive women with 77 breast lesions examined in consultation in a multidisciplinary breast cancer center between January and June 1998. Each patient's case was evaluated by a panel consisting of a medical oncologist, surgical oncologist, radiation oncologist, pathologist, diagnostic radiologist, and, when indicated, plastic surgeon. A comprehensive history and physical examination was performed, and the relevant mammograms, pathology slides, and medical records were reviewed. Treatment recommendations made before this evaluation were compared with the consensus recommendations made by the panel.



RESULTS

For the 75 patients, the multidisciplinary panel disagreed with the treatment recommendations from the outside physicians in 32 cases (43%), and agreed in 41 cases (55%). Two patients (3%) had no treatment recommendation before consultation. For the 32 patients with a disagreement, the treatment recommendations were breast-conservation treatment instead of mastectomy (n = 13; 41%) or reexcision (n = 2; 6%); further workup instead of immediate definitive treatment (n = 10; 31%); treatment based on major change in diagnosis on pathology review (n = 3; 9%); addition of postmastectomy radiation treatment (n = 3; 9%); or addition of hormonal therapy (n = 1; 3%).



CONCLUSIONS

The multidisciplinary breast cancer evaluation program provided an integrated program in which individual patients were evaluated by a team of physicians and led to a change in treatment recommendation for 43% (32 of 75) of the patients examined. This multidisciplinary program provided important second opinions for many patients with breast carcinoma. Cancer 2001;91:1231–7. © 2001 American Cancer Society.

https://acsjournals.onlinelibrary.wiley.com/doi/pdf/10.1002/1097-0142%2820010401%2991%3A7%3C1231%3A%3AAID-CNCR1123%3E3.0.CO%3B2-K

The impact of a multidisciplinary breast cancer center on recommendations for patient management: the University of Pennsylvania experience.

This review considers the feasibility of reducing or eliminating the three major categories of diagnostic errors in medicine: "No-fault errors" occur when the disease is silent, presents atypically, or mimics something more common. These errors will inevitably decline as medical science advances, new syndromes are identified, and diseases can be detected more accurately or at earlier stages. These errors can never be eradicated, unfortunately, because new diseases emerge, tests are never perfect, patients are sometimes noncompliant, and physicians will inevitably, at times, choose the most likely diagnosis over the correct one, illustrating the concept of necessary fallibility and the probabilistic nature of choosing a diagnosis. "System errors" play a role when diagnosis is delayed or missed because of latent imperfections in the health care system. These errors can be reduced by system improvements, but can never be eliminated because these improvements lag behind and degrade over time, and each new fix creates the opportunity for novel errors. Tradeoffs also guarantee system errors will persist, when resources are just shifted. "Cognitive errors" reflect misdiagnosis from faulty data collection or interpretation, flawed reasoning, or incomplete knowledge. The limitations of human processing and the inherent biases in using heuristics guarantee that these errors will persist. Opportunities exist, however, for improving the cognitive aspect of diagnosis by adopting system-level changes (e.g., second opinions, decision-support systems, enhanced access to specialists) and by training designed to improve cognition or cognitive awareness. Diagnostic error can be substantially reduced, but never eradicated.

Ronald L. Sirota

Papers

Mandatory second opinion surgical pathology at a large referral hospital.