Citations

Abstract The recent development of imaging and sequencing technologies enables systematic advances in the clinical study of lung cancer. Meanwhile, the human mind is limited in effectively handling and fully utilizing the accumulation of such enormous amounts of data. Machine learning-based approaches play a critical role in integrating and analyzing these large and complex datasets, which have extensively characterized lung cancer through the use of different perspectives from these accrued data. In this review, we provide an overview of machine learning-based approaches that strengthen the varying aspects of lung cancer diagnosis and therapy, including early detection, auxiliary diagnosis, prognosis prediction, and immunotherapy practice. Moreover, we highlight the challenges and opportunities for future applications of machine learning in lung cancer.

OBJECTIVE Stereotactic radiosurgery (SRS) is an effective treatment for intracranial metastatic disease, but its role in triple-negative breast cancer requires further study. Herein, the authors report overall survival (OS) and local tumor control in a multiinstitutional cohort with triple-negative breast cancer metastases treated with SRS. METHODS Patients treated from 2010 to 2019 at 9 institutions were included in this retrospective study if they had biopsy-proven triple-negative breast cancer with intracranial metastatic lesions treated with SRS. Patients were excluded if they had undergone prior SRS, whole-brain radiation therapy, or resection of the metastatic lesions. A retrospective chart review was conducted to determine OS, local control, and treatment efficacy. RESULTS Sixty-eight patients with 315 treated lesions were assessed. Patients had a median Karnofsky Performance Status of 80 (IQR 70–90) and age of 57 years (IQR 48–67 years). Most treated patients had 5 or fewer intracranial lesions, with 34% of patients having a single lesion. Treated lesions were small, having a median volume owf 0.11 cm3 (IQR 0.03–0.60 cm3). Patients were treated with a median margin dose of 18 Gy (IQR 18–20 Gy) to the median 71% isodose line (IQR 50%–84%). Overall, patients had a 1-year OS of 43% and 2-year OS of 20%. Most patients (88%) were followed until death, by which time local tumor progression had occurred in only 7% of cases. Furthermore, 76% of the lesions demonstrated regression. Tumor volume was correlated with local tumor progression (p = 0.012). SRS was very well tolerated, and only 3 patients (5%) developed symptomatic radiation necrosis. CONCLUSIONS SRS is a safe and efficacious treatment for well-selected patients with triple-negative breast cancer, especially for those with a favorable performance status and small- to moderate-volume metastatic lesions.

The clinical and largely unpredictable heterogeneity of phenotypes in patients with mitochondrial disorders demonstrates the ongoing challenges in the understanding of this semi-autonomous organelle in biology and disease. Previously, we used the gene-breaking transposon to create 1200 transgenic zebrafish strains tagging protein-coding genes (Ichino et al., 2020), including the lrpprc locus. Here, we present and characterize a new genetic revertible animal model that recapitulates components of Leigh Syndrome French Canadian Type (LSFC), a mitochondrial disorder that includes diagnostic liver dysfunction. LSFC is caused by allelic variations in the LRPPRC gene, involved in mitochondrial mRNA polyadenylation and translation. lrpprc zebrafish homozygous mutants displayed biochemical and mitochondrial phenotypes similar to clinical manifestations observed in patients, including dysfunction in lipid homeostasis. We were able to rescue these phenotypes in the disease model using a liver-specific genetic model therapy, functionally demonstrating a previously under-recognized critical role for the liver in the pathophysiology of this disease.