Colorectal cancer (CRC) is the second most common cancer in women and the third most common in men, with an increasing incidence. Pathology diagnosis complemented with prognostic and predictive biomarker information is the first step for personalized treatment. The increased diagnostic load in the pathology laboratory, combined with the reported intra- and inter-variability in the assessment of biomarkers, has prompted the quest for reliable machine-based methods to be incorporated into the routine practice. Recently, Artificial Intelligence (AI) has made significant progress in the medical field, showing potential for clinical applications. Herein, we aim to systematically review the current research on AI in CRC image analysis. In histopathology, algorithms based on Deep Learning (DL) have the potential to assist in diagnosis, predict clinically relevant molecular phenotypes and microsatellite instability, identify histological features related to prognosis and correlated to metastasis, and assess the specific components of the tumor microenvironment.

Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct histological patterns combined with molecular data for personalized treatment. Precise lung cancer classification from a single H&E slide can be challenging for a pathologist, requiring most of the time additional histochemical and special immunohistochemical stains for the final pathology report. According to WHO, small biopsy and cytology specimens are the available materials for about 70% of lung cancer patients with advanced-stage unresectable disease. Thus, the limited available diagnostic material necessitates its optimal management and processing for the completion of diagnosis and predictive testing according to the published guidelines. During the new era of Digital Pathology, Deep Learning offers the potential for lung cancer interpretation to assist pathologists’ routine practice. Herein, we systematically review the current Artificial Intelligence-based approaches using histological and cytological images of lung cancer. Most of the published literature centered on the distinction between lung adenocarcinoma, lung squamous cell carcinoma, and small cell lung carcinoma, reflecting the realistic pathologist’s routine. Furthermore, several studies developed algorithms for lung adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, and PD-L1 expression status estimation.

Most abdominal masses in the pediatric population derive from the ovaries. Ovarian masses can occur in all ages, although their incidence, clinical presentation and histological distribution vary among different age groups. Children and adolescents may develop non-neoplastic ovarian lesions, such as functional cysts, endometrioma, torsion, abscess and lymphangioma as well as neoplasms, which are divided into germ cell, epithelial, sex-cord stromal and miscellaneous tumors. Germ cell tumors account for the majority of ovarian neoplasms in the pediatric population, while adults most frequently present with epithelial tumors. Mature teratoma is the most common ovarian neoplasm in children and adolescents, whereas dysgerminoma constitutes the most frequent ovarian malignancy. Clinical manifestations generally include abdominal pain, palpable mass, nausea/vomiting and endocrine alterations, such as menstrual abnormalities, precocious puberty and virilization. During the investigation of pediatric ovarian masses, the most important objective is to evaluate the likelihood of malignancy since the management of benign and malignant lesions is fundamentally different. The presence of solid components, large size and heterogenous appearance on transabdominal ultrasonography, magnetic resonance imaging and computed tomography indicate an increased risk of malignancy. Useful tumor markers that raise concern for ovarian cancer in children and adolescents include alpha-fetoprotein, lactate dehydrogenase, beta subunit of human chorionic gonadotropin, cancer antigen 125 and inhibin. However, their serum levels can neither confirm nor exclude malignancy. Management of pediatric ovarian masses needs to be curative and, when feasible, function-preserving and minimally invasive. Children and adolescents with an ovarian mass should be treated in specialized centers to avoid unnecessary oophorectomies and ensure the best possible outcome.

Primary bone lymphoma (PBL) is a rare neoplasm of malignant lymphoid cells presenting with one or more bone lesions without nodal or other extranodal involvement. It accounts for approximately 1% of all lymphomas and 7% of malignant primary bone tumors. Diffuse large B-cell lymphoma (DLBCL), not otherwise specified (NOS) represents the predominant histological type and constitutes over 80% of all cases. PBL may occur at all ages with a typical diagnosis age of 45–60 years and a slight male predominance. Local bone pain, soft tissue edema, palpable mass and pathological fracture are the most common clinical features. Diagnosis of the disease, which is frequently delayed due to its non-specific clinical presentation, is based on the combination of clinical examination and imaging studies and confirmed by combined histopathological and immunohistochemical examination. PBL can develop in any part of the skeleton, although it occurs most commonly in the femur, humerus, tibia, spine and pelvis. The imaging appearance of PBL is highly variable and unspecific. In terms of the cell-of-origin, most cases of primary bone DLBCL (PB-DLBCL), NOS belong to the germinal center B-cell-like subtype and specifically originate from germinal center centrocytes. PB-DLBCL, NOS has been considered a distinct clinical entity based on its particular prognosis, histogenesis, gene expression and mutational profile and miRNA signature. PBL carries a favorable prognosis, especially when treated with combined chemoradiotherapy.

Background: Positron emission tomography (PET) is a valuable tool for the assessment of lymphoma, while artificial intelligence (AI) holds promise as a reliable resource for the analysis of medical images. In this context, we systematically reviewed the applications of deep learning (DL) for the interpretation of lymphoma PET images. Methods: We searched PubMed until 11 September 2024 for studies developing DL models for the evaluation of PET images of patients with lymphoma. The risk of bias and applicability concerns were assessed using the prediction model risk of bias assessment tool (PROBAST). The articles included were categorized and presented based on the task performed by the proposed models. Our study was registered with the international prospective register of systematic reviews, PROSPERO, as CRD42024600026. Results: From 71 papers initially retrieved, 21 studies with a total of 9402 participants were ultimately included in our review. The proposed models achieved a promising performance in diverse medical tasks, namely, the detection and histological classification of lesions, the differential diagnosis of lymphoma from other conditions, the quantification of metabolic tumor volume, and the prediction of treatment response and survival with areas under the curve, F1-scores, and R² values of up to 0.963, 87.49%, and 0.94, respectively. Discussion: The primary limitations of several studies were the small number of participants and the absence of external validation. In conclusion, the interpretation of lymphoma PET images can reliably be aided by DL models, which are not designed to replace physicians but to assist them in managing large volumes of scans through rapid and accurate calculations, alleviate their workload, and provide them with decision support tools for precise care and improved outcomes.