Tissue classification and diagnosis of colorectal cancer histopathology images using deep learning algorithms. Is the time ripe for clinical practice implementation?

Abstract

Colorectal cancer is one of the most prevalent types of cancer, with histopathologic examination of biopsied tissue samples remaining the gold standard for diagnosis. During the past years, artificial intelligence (AI) has steadily found its way into the field of medicine and pathology, especially with the introduction of whole slide imaging (WSI). The main outcome of interest was the composite balanced accuracy (ACC) as well as the F1 score. The average reported ACC from the collected studies was 95.8 ±3.8%. Reported F1 scores reached as high as 0.975, with an average of 89.7 ±9.8%, indicating that existing deep learning algorithms can achieve in silico distinction between malignant and benign. Overall, the available state-of-the-art algorithms are non-inferior to pathologists for image analysis and classification tasks. However, due to their inherent uniqueness in their training and lack of widely accepted external validation datasets, their generalization potential is still limited.

LGR6 is a prognostic biomarker for less differentiated tumors in lymph nodes of colon cancer patients

“…It is unlikely that the results presented here would have been possible to obtain by histopathology or even immunohistochemistry with specific antibodies supported by artificial intelligence (AI) deep learning algorithms, because only a small portion of the LN volume is analyzed by these methods ( 39 , 40 ). We showed in a previous study that disseminated tumor cells are heterogeneously distributed in the LN and metastases can be missed if only a small volume is analyzed ( 41 ).…”

Case report: Successful treatment of advanced colon cancer in an eighty-year-old man with long-term and multi-stage endoscopic minimally invasive therapy

“…However, there are also limitations, such as how frequently and to what extent endoscopic resection should be performed and which older patients would benefit. Moreover, the early and accurate diagnosis of colon cancer is also vital to provide the chance for minimally invasive therapy, and some studies have reported deep learning algorithms have the potential to improve the accuracy and efficacy of CRC detection ( 20 , 21 ). Therefore, further clinical practice and investigations are needed to apply deep learning algorithms to the classification and diagnosis of CRC and invasive endoscopic therapy for the therapy of CRC.…”

The efficacy and safety of neoadjuvant chemoradiotherapy combined with immunotherapy for locally advanced rectal cancer patients: a systematic review

“…Although the clinical strategy of nCRT combined with immunotherapy had great potential, there were still many areas that need to be improved. Artificial intelligence and its subtypes, especially deep learning(DL) played an increasing role in the diagnosis and prognosis of LARC, DL protocols seemed to help physicians optimize the strategy of neoadjuvant treatment of LARC by improving diagnostic accuracy, increasing clinician experience, and minimizing diagnostic subjectivity among physicians ( 40 , 41 ).…”