Artificial Intelligence in Radiotherapy: A Philosophical Perspective.

The increasing uptake of machine learning solutions for segmentation and planning leaves no doubt that artificial intelligence (AI) will soon be providing input into a range of radiotherapy procedures. Although this promises to deliver increased speed and accuracy, the future role of AI in relation to radiotherapy should be thought through carefully. There is currently a gap between published developments and widespread adoption, which provides some space to prepare the workforce and to consider the implications on practice. It is rare to find philosophical input into a medical journal, but the advent of AI makes this perspective increasingly important. Philosophical insight can help explore the potential impact of AI, in particular, on human creativity and oversight. Without this perspective, we run the risk of focusing solely on the immediate logistical impact on patients and departments. This commentary identifies three key aspects of radiotherapy that the authors feel would suffer most under AI control: creativity, innovation, and patient safety, which all demand uniquely human attributes. The article also provides insight from a philosophical perspective with regard to human consciousness, ethics, and empathy. Philosophically we should, perhaps, retain ethical concerns about the widening role of AI in radiotherapy beyond simple quantitative interpretation and image processing. As developments continue, we have time to determine how our roles will evolve and to establish a framework for ensuring appropriate human input into patient care. Most importantly, we must start to embed a philosophical approach to adoption of AI technology from the outset if we are to prepare ourselves for the challenge that lies ahead.

An investigation of genomic base distribution.

While veritable oceans of ink have been spilled over the base distributions within genes, the literature is virtually silent on large scale intra genomic base distribution. To address this issue, we have examined approximately 3400 chromosomal sequences from approximately 2000 entire genomes-including DNA and RNA, single- and double-stranded, coding and non-coding genomes. For each sequence the mean, variance, skewness, and kurtosis for each base were computed along with the genome base composition. The main findings are: (1) there is no simple relationship between these statistics and the base composition of the genome, (2) in non-viral genomes, base distribution is non-uniform, (3) base distribution in non-eukaryotic genomes obeys a number of simple rules, (4) these rules are not dependent on the presence of coding sequences, (5) bacterial genomes in particular are unusually compliant with these rules, and (6) eukaryotes have a unique pattern of base distribution.

Molecular diagnosis of Ewing sarcoma/primitive neuroectodermal tumor in routinely processed tissue: a comparison of two FISH strategies and RT-PCR in malignant round cell tumors.

Ewing sarcoma/primitive neuroectodermal tumor (EWS/PNET) is a diagnostically challenging malignant round cell tumor with signature translocations involving the EWS gene. These translocations are detectable with both reverse transcriptase-polymerase chain reaction (RT-PCR) and fluorescence in situ hybridization (FISH) in formalin-fixed paraffin-embedded tissue. However, RT-PCR is less sensitive in formalin-fixed paraffin-embedded than frozen tissue. Similarly, commercial FISH probes have recently become available, but have yet to be rigorously tested in the clinical setting. Therefore, we have compared RT-PCR with FISH using 'home brew' fusion probes for Ewing sarcoma (EWS)-FLI1 and a commercial EWS break apart probe set in 67 archival round cell tumors, including 27 EWS/PNETs. Sensitivities and specificities for both FISH assays were 91 and 100%, respectively, whereas RT-PCR had a sensitivity of 54% and a specificity of 85%. The break apart strategy was easier to interpret than probe fusion approach. We conclude that FISH is a more sensitive and reliable ancillary technique than RT-PCR for the diagnosis of EWS/PNET in formalin-fixed paraffin-embedded tissue, although the latter provides additional information regarding fusion transcript subtype and prognosis. The commercial break apart probe set is both readily available and easy to interpret, making it particularly attractive. Nonetheless, complex round cell tumors often benefit from molecular testing with multiple methods.

A test of Chargaff's second rule.

In 1968, Chargaff and his colleagues discovered a rule in Bacillus subtilis: in single stranded DNA, A=T and C=G. This rule has since been confirmed many times in other bacterial and eukaryotic genomes. To the best of our knowledge, this rule has not been tested before in either single stranded DNA or RNA genomes. Over 3400 genomic sequences were examined here and included for the first time both double and single stranded DNA and RNA genomes. We found that: (1) with the exception of the organellar DNA, this parity rule holds for all types of double stranded DNA genomes and (2) that this rule fails to hold for other types of genomes. The parity rule appears to be a selective force on genome evolution and codon use.

Cytogenetic and molecular cytogenetic evidence of recurrent 8q24.1 loss in osteochondroma.

Osteochondroma most frequently arises sporadically and as a solitary lesion, but may also arise as multiple lesions characterizing the autosomal dominant disorder hereditary multiple exostoses (HME) and the contiguous gene-deletion syndrome, Langer-Giedion syndrome (LGS). Various germline mutations of two putative tumor suppressor genes, EXT1 localized to 8q24.1 and EXT2 localized to 11p11 approximately p12, have been demonstrated in HME families. Constitutional chromosomal deletions or structural rearrangements of 8q24.1 are seen in LGS. Cytogenetic reports of sporadic and hereditary osteochondromas are few, but have revealed loss or structural rearrangements of 8q24.1 in a small number of tumors. In the current study, karyotypic evaluation of 37 osteochondroma specimens (both sporadic and hereditary lesions) revealed chromosomal anomalies of 8q24.1 in 10 specimens (27%). In an effort to determine the presence and frequency of submicroscopic deletions, molecular cytogenetic studies were performed on this same set of tumors utilizing a chromosome 8 specific centromeric probe and an 8q24.1 cosmid probe (locus D8S51, within the minimal LGS deletion region). Loss of the 8q24.1 locus was detected by fluorescence in situ hybridization in 27 of 34 (79%) osteochondroma specimens analyzed including all 10 specimens exhibiting chromosome 8 abnormalities cytogenetically. These findings indicate that a significant subset of osteochondromas harbor genetic aberrations at the EXT1 locus and suggest that loss or mutation of EXT1 plays an important role in the pathogenesis of sporadic as well as hereditary osteochondromas.