Transforming breast cancer care: harnessing the power of artificial intelligence and imaging for predicting pathological complete response. a narrative review.

This narrative review explores the transformative potential of Artificial Intelligence (AI) and advanced imaging techniques in predicting Pathological Complete Response (pCR) in Breast Cancer (BC) patients undergoing Neo-Adjuvant Chemotherapy (NACT). Summarizing recent research findings underscores the significant strides made in the accurate assessment of pCR using AI, including deep learning and radiomics. Such AI-driven models offer promise in optimizing clinical decisions, personalizing treatment strategies, and potentially reducing the burden of unnecessary treatments, thereby improving patient outcomes. Furthermore, the review acknowledges the potential of AI to address healthcare disparities in Low- and Middle-Income Countries (LMICs), where accessible and scalable AI solutions may enhance BC management. Collaboration and international efforts are essential to fully unlock the potential of AI in BC care, offering hope for a more equitable and effective approach to treatment worldwide.

The discerning influence of dynamic contrast-enhanced MRI in anticipating molecular subtypes of breast cancer through the artistry of artificial intelligence - a narrative review.

Radio genomics is an exciting new area that uses diagnostic imaging to discover genetic features of diseases. In this review, we carefully examined existing literature to evaluate the role of artificial intelligence (AI) and machine learning (ML) on dynamic contrastenhanced MRI (DCE-MRI) data to distinguish molecular subtypes of breast cancer (BC). Implications to noninvasive assessment of molecular subtype include reduction in procedure risks, tailored treatment approaches, ability to examine entire lesion, follow-up of tumour biology in response to treatment and evaluation of treatment resistance and failure secondary to tumour heterogeneity. Recent studies leverage radiomics and AI on DCE-MRI data for reliable, non-invasive breast cancer subtype classification. This review recognizes the potential of AI to predict the molecular subtypes of breast cancer non-invasively.

Use of National Institute for Health and Care Excellence head injury guidelines among patients with delayed presentation after head trauma can lead to missed traumatic brain injury: a 5-year institutional review.

Introduction: In 2014, traumatic brain injury (TBI) caused 3 million ER visits, hospitalizations, and deaths in the US. The National Institute for Health and Care Excellence (NICE) guidelines, initially generated using data from patients presenting within 24 h of head trauma, are used to determine the need for head computed tomography (CT) scan in patients after 24 h. The authors wanted to determine the proportion of CT scans for head trauma performed at our center in late presenters (>24 h after head trauma), the incidence of intracranial pathology in early (24 h) versus late (>24 h) presenters, and the sensitivity of the NICE guidelines for TBI in these two subpopulations. Methods: A retrospective chart review was conducted at a tertiary care center in Karachi. All people (>16) who had a head CT for head trauma from 2010 to 2015 were included. Age, sex, primary diagnosis, comorbid disorders, mechanism-of-injury, duration (in hours) from head trauma to presentation, site, and extent of injury (injury severity scale), hospital stay, number and details of surgical procedures, CT scan findings, other injuries, and mortality were recorded. Means were compared using the Independent Sample t-test, while categorical variables were compared using χ2. Multivariate logistic regression analyses were used to identify TBI predictors. Results: The authors found 2009 eligible patients; seven were excluded due to incomplete medical records. The final statistical analysis comprised 2002 head trauma patients. Overall, 52% of early and late presenters had severe injuries, and 2.3% died. 32.2% of patients with head trauma had CT after 24 h. Early presenters were 46.7% traumatized, while late presenters were 63%. The NICE guidelines were 93% sensitive for early presenters and 83% for late presenters with traumatic intracranial injury. Conclusion: Patients coming to the emergency department after 24 h of head trauma are a large proportion of the overall head trauma population. The NICE guidelines for late-presenting head injuries are less sensitive and may overlook intracranial injuries if imaging is not performed.

Correlation Of Computerized Tomography (CT) Severity Score For COVID-19 Pneumonia With Clinical Outcomes.

BACKGROUND: Though various computerized tomography (CT) severity scores have been described for risk prognostication for coronavirus disease 2019 (COVID-19), most are challenging to calculate and have variable inter-observer agreement. The objective of this study was to develop a simple CT severity score (CT-SS) with good inter-observer agreement and assess its correlation with clinical outcome. METHODS: This retrospective study was conducted at the Aga Khan University Hospital (AKUH), from April-August 2020. All patients who were PCR positive for COVID-19 and underwent CT chest examination at AKUH were included. Severity of disease was described on the basis of a 10-point CT severity score (CT-SS) devised at our institution. CT-SS were categorized as Low (0-7) and High (8-10). Inter-observer reliability between radiologist and COVID-19 intensivist was assessed using the Kappa statistic. RESULTS: A total of 73 patients were included, the majority male (58.9%) with mean age 55.8±13.93 years. The CT-SS rated on 0-10 showed substantial inter-observer reliability between radiologist and intensivist with a Kappa statistic of 0.78. Patients with CT-SS 8-10 had a significantly higher ICU admission & intubation rate (53.8% vs. 23.5%) and mortality rate (35.9% vs. 11.8%; p=0.017), as compared to those with CT-SS 0-7. CONCLUSIONS: We conclude that the described CT severity score (CT-SS) is a quick, effective, and easily reproducible tool for prediction of adverse clinical outcome in patients with COVID 19 pneumonia. The tool shows good inter-observer agreement when calculated by radiologist and physician independently.

Cardiac hydatid cyst presenting as ventricular arrhythmia: a case report.

BACKGROUND: Hydatid disease caused by Echinococcus granulosus commonly involves the liver followed by lungs. Cardiac involvement is a rare occurrence and presents a challenging scenario. CASE PRESENTATION: Our case describes a middle-aged gentleman who presented to the emergency room with an episode of sudden loss of consciousness resulting from ventricular tachycardia. After successful cardiac resuscitation, the patient underwent imaging that showed a lesion compatible with hydatid cyst. Surgical treatment with pharmacologic coverage was provided which resulted in good clinical outcome. CONCLUSIONS: The case highlights rare occurrence of isolated cardiac hydatid disease presenting as cardiac arrhythmia in contrast to its common routine outpatient presentation involving the liver and lungs. Good knowledge of the unusual presentations and its epidemiology is essential to the proper management of such patients.

Role of contrast enhanced computed tomography in assessing cervical lymph node metastases in oral cavity squamous cell carcinoma.

OBJECTIVE: To evaluate the diagnostic accuracy of contrast-enhanced computed tomography scan in detecting cervical nodal metastasis in oral cavity squamous cell carcinoma. METHODS: The retrospective cross-sectional study was conducted at Aga Khan University Hospital, Karachi, Pakistan. and comprised records from January 1, 2015, to October 31, 2016, of patients diagnosed with oral cavity squamous cell carcinoma and who underwent surgical resection of primary tumour along with neck dissection after having a contrast-enhanced computed tomography scan of head and neck. Diagnostic accuracy of the scans was calculated using final histopathology as the gold standard. All scans were reviewed by a consultant radiologist. Data was analysed using SPSS 23. RESULTS: Of the 100 patients whose records were reviewed, 70(70%) were female, 55(55%) had buccal and 32(32%) had tongue cancer.. The scans had sensitivity 83%, specificity 61.7%, positive predictive value 70.9%, negative predictive value 76.3% and overall diagnostic accuracy 73%. CONCLUSIONS: Computed tomography scan was found to be a useful tool for preoperative staging of oral cavity squamous cell carcinoma. However, due to low specificity and negative predictive value, elective neck dissection should still be done in a negative scan for cervical lymph node metastases.

Dental caries prevalence and its association with fluoride level in drinking water in Sana'a, Yemen.

OBJECTIVES: Dental caries is the most prevalent chronic condition affecting schoolchildren worldwide. This study is aimed to assess the prevalence of dental caries among schoolchildren in urban and rural districts of Sana'a governorate, Yemen, and to investigate the correlation between caries experience and level of fluoride in drinking water, age, gender, and residence. MATERIALS AND METHODS: This school-based survey involved 17,599 schoolchildren (aged 6-12 years), of whom 9623 were boys and 7976 were girls. We used decay-missing-filled teeth/decay-filled teeth (DMFT/dft) indices to evaluate dental caries experience. In addition, fluoride concentration in drinking water was investigated. RESULTS: Around 67.6% of children had dental caries. Children residing in urban districts had significantly higher mean scores of DMFT/dft than those in rural areas (P < 0.05). A significant negative correlation between caries experience and fluoride level was found (P < 0.05), with the lowest dft/DMFT scores at the optimum fluoride level of 0.61-2 ppm and the highest at two extremes, 0.0-0.4 ppm and >2 ppm. CONCLUSION: This survey found a very high prevalence of caries among schoolchildren in Yemen. There was also an inverse relation between dental caries experience and fluoride levels.